[Image]

 

Ruslan Salakhutdinov
PhD Student
Department of Computer Science
University of Toronto
6 King's College Rd.
Toronto, Ontario, Canada
M5S 3G4
Email: rsalakhu (at) cs (dot) toronto (dot) edu
Office: Pratt 265A

Starting Sep 2009, I will be a postdoctoral fellow at MIT. Visit my new homepage.


I am a PhD student at University of Toronto, where I work with Geoffrey Hinton and Sam Roweis.


NIPS 2009 Workshop on Approximate Learning of Large Scale Graphical Models: Theory and Applications here
(that I am organizing together with Amir Globerson and David Sontag).

ICML09 Workshop on Learning Feature Hierarchies here

Several Representative Papers:

Bayesian Probabilistic Matrix Factorization using MCMC.
Ruslan Salakhutdinov and Andriy Mnih
In 25th International Conference on Machine Learning (ICML-2008) [bibtex] [ps.gz],[ pdf]

Learning and Evaluating Boltzmann Machines.
Ruslan Salakhutdinov
Technical Report UTML TR 2008-002, Dept. of Computer Science, University of Toronto
[bibtex] [ps.gz][ pdf]
This paper introduces a new Boltzmann machine learning algorithm that combines variational techniques and MCMC.

Deep Boltzmann Machines.
Ruslan Salakhutdinov and Geoffrey Hinton
12th International Conference on Artificial Intelligence and Statistics (2009).
[bibtex] [ps.gz][ pdf]


Recent Papers

Ruslan Salakhutdinov.
Learning in Markov Random Fields using Tempered Transitions
To appear in NIPS*22

Ruslan Salakhutdinov and Geoffrey Hinton.
Replicated Softmax: an Undirected Topic Model.
To appear in NIPS*22

Ilya Sutskever, Ruslan Salakhutdinov, and Josh Tenenbaum.
Modelling Relational Data using Bayesian Clustered Tensor Factorization.
To appear in NIPS*22

John Langford, Ruslan Salakhutdinov and Tong Zhang.
Learning Nonlinear Dynamic Models.
Proceedings of the 26th International Conference on Machine Learning (ICML), 2009.
[bibtex] [ps.gz][ pdf]

Hanna M. Wallach, Iain Murray, Ruslan Salakhutdinov and David Mimno.
Evaluation Methods for Topic Models.
Proceedings of the 26th International Conference on Machine Learning (ICML), 2009.
[bibtex] [ pdf]

Iain Murray and Ruslan Salakhutdinov.
Evaluating probabilities under high-dimensional latent variable models.
Neural Information Processing Systems 21 (NIPS 2009)
[bibtex] [ pdf], Jan 2009


Recent Talks

  • Deep Boltzmann Machines (ps.gz, pdf).
    Snowbird workshop, April 2009.

  • I was co-organizing Deep Learning Workshop: Foundations and Future Directions, NIPS 2007.

  • Deep Belief Nets (ps.gz, pdf).
    Snowbird workshop, March 2007.
    Demo and explanation of Digits and Faces.


    [ Home | Information | Research | Background ]

    Ruslan Salakhutdinov, Artificial Intelligence Group, Toronto Computer Science || www.cs.toronto.edu/~rsalakhu